-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
点云转表面网格 #4
Comments
[测试] 尝试了使用 open3d 中的 PoissonRecon 算法将点云转为 .obj 格式的网格,代码如下 import open3d as o3d
# Load the .pcd file
pcd = o3d.io.read_point_cloud("chuancang_model.pcd")
# Create a mesh from the point cloud
mesh, densities = o3d.geometry.TriangleMesh.create_from_point_cloud_poisson(pcd, depth=9)
# Save the mesh as a .obj file
o3d.io.write_triangle_mesh("chuancang_model.obj", mesh) 点云可视化如下: 导出的 .obj 文件可视化如下: [分析] 由于建图时扫描出来的点云是非常稀疏的,所以很多地方会把误认为是洞。 |
[Research] 点云转网格是一个比较热门的研究,随便搜了一下,就找到了 Point2Mesh: A Self-Prior for Deformable Meshes 然后通过 Connected Paper 找到了该领域的论文 关系图 |
[测试] 用 Point2Mesh: A Self-Prior for Deformable Meshes 将点云转网格。
Point2Mesh 有些年头了,所以之前作者给出的环境现在不能用了。以下是我配置环境的过程,我的 GPU 是 RTX 3070 Ti Laptop, cuda 是 12.3
需要修改代码以适应最新版的 pytorch 以及 pytorch3d。 这里我是参考了这个 github issue
我的 GPU 只有 8g 显存,跑了作者给的例子 |
上面的方法从原理上就不适合我们的场景,因为它默认了物体是从外表面扫描的,但我们的场景是扫描的内部表面。 |
实现从PCL 点云数据结构转换为三维表面网格
The text was updated successfully, but these errors were encountered: